Large-Scale Unbiased Neuroimage Indexing via 3D GPU-SIFT Filtering and Keypoint Masking

Pepin, Étienne; Carluer, Jean-Baptiste; Chauvin, Laurent; Toews, Matthew; Harmouche, Rola

doi:10.1007/978-3-030-66843-3_11

Cited by 2 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Feature extraction requires approximately 3 sec. / per image via a GPU implementation of 3D SIFT extraction [69], and results in an average of 1,400 features per image, for a total of 1,488,065 features. Approximate kNN correspondences between appearance descriptors are identified across the entire database using efficient KD-tree indexing [23], where lookup requires 0.8 sec.…”

Section: A Image Data and Preprocessingmentioning

confidence: 99%

Efficient Pairwise Neuroimage Analysis Using the Soft Jaccard Index and 3D Keypoint Sets

Chauvin

Kumar

Desrosiers

et al. 2022

IEEE Trans. Med. Imaging

Self Cite

View full text Add to dashboard Cite

We propose a novel pairwise distance measure between variable-sized sets of image keypoints for the purpose of large-scale medical image indexing. Our measure generalizes the Jaccard index to account for soft set equivalence (SSE) between set elements, via an adaptive kernel framework accounting for uncertainty in keypoint appearance and geometry. Novel kernels are proposed to quantify the variability of keypoint geometry in location and scale. Our distance measure may be estimated between N 2 image pairs in O(N log N ) operations via keypoint indexing. Experiments validate our method in predicting 509,545 pairwise relationships from T1-weighted MRI brain volumes of monozygotic and dizygotic twins, siblings and halfsiblings sharing 100%-25% of their polymorphic genes. Soft set equivalence and keypoint geometry kernels outperform standard hard set equivalence (HSE) in predicting family relationships. High accuracy is achieved, with monozygotic twin identification near 100% and several cases of unknown family labels, due to errors in the genotyping process, are correctly paired with family members. Software is provided for efficient fine-grained curation of large, generic image datasets.

show abstract

Section: A Image Data and Preprocessingmentioning

confidence: 99%

Efficient Pairwise Neuroimage Analysis Using the Soft Jaccard Index and 3D Keypoint Sets

Chauvin

Kumar

Desrosiers

et al. 2022

IEEE Trans. Med. Imaging

Self Cite

View full text Add to dashboard Cite

show abstract

“…Our GPU-optimized 3D SIFT-CNN method was first described and used in the context of brain MRI analysis (Pepin et al, 2020). The original 3D SIFT-Rank method has been used in a variety of keypoint applications analyzing 3D images of the human body.…”

Section: Introductionmentioning

confidence: 99%

“…In particular, we target the Gaussian convolution, difference of Gaussians, sub-sampling and 4D extraction. This work was the first published GPU implementation of the 3D SIFT algorithm, first validated in the context of brain image indexing (Pepin et al, 2020). Previously, GPU processing was used to speed up the SIFT algorithm for 2D image data (Heymann et al, 2007), in real-time (Lalonde et al, 2007) and video processing contexts (Fassold and Rosner, 2015), and high-dimensional feature matching (Garcia et al, 2010) applications, and for use on mobile devices (Rister et al, 2013).…”

Section: Introductionmentioning

confidence: 99%

GPU optimization of the 3D Scale-invariant Feature Transform Algorithm and a Novel BRIEF-inspired 3D Fast Descriptor

Carluer¹,

Chauvin²,

Luo³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

This work details a highly efficient implementation of the 3D scale-invariant feature transform (SIFT) algorithm, for the purpose of machine learning from large sets of volumetric medical image data. The primary operations of the 3D SIFT code are implemented on a graphics processing unit (GPU), including convolution, sub-sampling, and 4D peak detection from scale-space pyramids. The performance improvements are quantified in keypoint detection and image-to-image matching experiments, using 3D MRI human brain volumes of different people. Computationally efficient 3D keypoint descriptors are proposed based on the Binary Robust Independent Elementary Feature (BRIEF) code, including a novel descriptor we call Ranked Robust Independent Elementary Features (RRIEF), and compared to the original 3D SIFT-Rank method(Toews and Wells III, 2013). The GPU implementation affords a speedup of approximately 7X beyond an optimised CPU implementation, where computation time is reduced from 1.4 seconds to 0.2 seconds for 3D volumes of size (145, 174, 145) voxels with approximately 3000 keypoints. Notable speedups include the convolution operation (20X), 4D peak detection (3X), sub-sampling (3X), and difference-of-Gaussian pyramid construction (2X). Efficient descriptors offer a speedup of 2X and a memory savings of 6X compared to standard SIFT-Rank descriptors, at a cost of reduced numbers of keypoint correspondences, revealing a trade-off between computational efficiency and algorithmic performance. The speedups gained by our implementation will allow for a more efficient analysis on larger data sets. Our optimized GPU implementation of the 3D SIFT-Rank extractor is available at (https://github.com/CarluerJB/3D_SIFT_CUDA).

show abstract

Large-Scale Unbiased Neuroimage Indexing via 3D GPU-SIFT Filtering and Keypoint Masking

Cited by 2 publications

References 20 publications

Efficient Pairwise Neuroimage Analysis Using the Soft Jaccard Index and 3D Keypoint Sets

Efficient Pairwise Neuroimage Analysis Using the Soft Jaccard Index and 3D Keypoint Sets

GPU optimization of the 3D Scale-invariant Feature Transform Algorithm and a Novel BRIEF-inspired 3D Fast Descriptor

Contact Info

Product

Resources

About